developer_uid: Hastagaras
submission_id: hastagaras-l3-clove-8b_v1
model_name: hastagaras-l3-clove-8b_v1
model_group: Hastagaras/L3-Clove-8B
status: torndown
timestamp: 2024-04-26T07:43:43+00:00
num_battles: 5532
num_wins: 3142
celo_rating: 1198.66
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Clove-8B
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-l3-clove-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Clove-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-26
win_ratio: 0.5679681851048446
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.0, 'stopping_words': ['\n', '###', '</s>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instructions:\n\nWrite {bot_name}'s next reply with genuine feelings and emotions based on the exact {bot_name}'s persona.\n\n{memory}", 'prompt_template': "\n\n### Input:\n\n{user_name}: Let's start the roleplay.\n\n### Response:\n\n{bot_name}: {prompt}", 'bot_template': '\n\n### Response:\n\n{bot_name}: {message}', 'user_template': '\n\n### Input:\n\n{user_name}: {message}', 'response_template': '\n\n### Response:\n\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-clove-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-clove-8b-v1-mkmlizer to finish
hastagaras-l3-clove-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-clove-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-clove-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-clove-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-clove-8b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
hastagaras-l3-clove-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-clove-8b-v1-mkmlizer: Downloaded to shared memory in 28.658s
hastagaras-l3-clove-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-clove-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-clove-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:03, 67.57it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 77.58it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00, 24.09it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-clove-8b-v1-mkmlizer: quantized model in 21.352s
hastagaras-l3-clove-8b-v1-mkmlizer: Processed model Hastagaras/L3-Clove-8B in 51.613s
hastagaras-l3-clove-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-clove-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-clove-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-clove-8b-v1
hastagaras-l3-clove-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-clove-8b-v1/special_tokens_map.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-clove-8b-v1/tokenizer_config.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-clove-8b-v1/config.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-clove-8b-v1/tokenizer.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-clove-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-clove-8b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-l3-clove-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-clove-8b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hastagaras-l3-clove-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-clove-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-clove-8b-v1-mkmlizer: Saving duration: 0.249s
hastagaras-l3-clove-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.349s
hastagaras-l3-clove-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-clove-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-clove-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward
hastagaras-l3-clove-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward/special_tokens_map.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward/tokenizer_config.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward/merges.txt
hastagaras-l3-clove-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward/config.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward/vocab.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward/tokenizer.json
hastagaras-l3-clove-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-clove-8b-v1_reward/reward.tensors
Job hastagaras-l3-clove-8b-v1-mkmlizer completed after 83.27s with status: succeeded
Stopping job with name hastagaras-l3-clove-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-clove-8b-v1
Waiting for inference service hastagaras-l3-clove-8b-v1 to be ready
Inference service hastagaras-l3-clove-8b-v1 ready after 30.17014169692993s
Pipeline stage ISVCDeployer completed in 37.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.109980821609497s
Received healthy response to inference request in 1.2488288879394531s
Received healthy response to inference request in 1.2447867393493652s
Received healthy response to inference request in 1.2839715480804443s
Received healthy response to inference request in 1.2602920532226562s
5 requests
0 failed requests
5th percentile: 1.2455951690673828
10th percentile: 1.2464035987854003
20th percentile: 1.2480204582214356
30th percentile: 1.2511215209960938
40th percentile: 1.255706787109375
50th percentile: 1.2602920532226562
60th percentile: 1.2697638511657714
70th percentile: 1.2792356491088868
80th percentile: 1.449173402786255
90th percentile: 1.779577112197876
95th percentile: 1.9447789669036863
99th percentile: 2.076940450668335
mean time: 1.4295720100402831
Pipeline stage StressChecker completed in 7.77s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-clove-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-clove-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-clove-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-clove-8b-v1 is running
admin requested tearing down of hastagaras-l3-cukai-8b-dpo_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-cukai-8b-dpo-v2 is running
Tearing down inference service hastagaras-l3-clove-8b-v1
Toredown service hastagaras-l3-clove-8b-v1
Pipeline stage ISVCDeleter completed in 4.38s
Tearing down inference service hastagaras-l3-cukai-8b-dpo-v2
Running pipeline stage MKMLModelDeleter
Toredown service hastagaras-l3-cukai-8b-dpo-v2
Cleaning model data from S3
Cleaning model data from model cache
Pipeline stage ISVCDeleter completed in 3.80s
Running pipeline stage MKMLModelDeleter
Deleting key hastagaras-l3-clove-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-cukai-8b-dpo-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-cukai-8b-dpo-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-clove-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key hastagaras-l3-clove-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-clove-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-clove-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-clove-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.23s
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cukai-8b-dpo-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
hastagaras-l3-clove-8b_v1 status is now torndown due to DeploymentManager action